Category: machinelearning

Auto Added by WPeMatico

Adversarial Machine Learning and the CFAA

Posted on By infossl
academicpapers, courts, fraud, machinelearning, Security technology

I just co-authored a paper on the legal risks of doing machine learning research, given the current state of the Computer Fraud and Abuse Act: Abstract: Adversarial Machine Learning is booming with ML researchers increasingly targeting commercial ML systems such as those used in Facebook, Tesla, Microsoft, IBM, Google to demonstrate vulnerabilities. In this paper, … Read More “Adversarial Machine Learning and the CFAA” »

Fawkes: Digital Image Cloaking

Posted on By infossl
academicpapers, facerecognition, machinelearning, Security technology, socialmedia

Fawkes is a system for manipulating digital images so that they aren’t recognized by facial recognition systems. At a high level, Fawkes takes your personal images, and makes tiny, pixel-level changes to them that are invisible to the human eye, in a process we call image cloaking. You can then use these “cloaked” photos as … Read More “Fawkes: Digital Image Cloaking” »

Identifying a Person Based on a Photo, LinkedIn and Etsy Profiles, and Other Internet Bread Crumbs

Posted on By infossl
identification, machinelearning, police, Security technology

Interesting story of how the police can identify someone by following the evidence chain from website to website. According to filings in Blumenthal’s case, FBI agents had little more to go on when they started their investigation than the news helicopter footage of the woman setting the police car ablaze as it was broadcast live … Read More “Identifying a Person Based on a Photo, LinkedIn and Etsy Profiles, and Other Internet Bread Crumbs” »

Availability Attacks against Neural Networks

Posted on By infossl
academicpapers, machinelearning, Security technology, securityengineering

New research on using specially crafted inputs to slow down machine-learning neural network systems: Sponge Examples: Energy-Latency Attacks on Neural Networks shows how to find adversarial examples that cause a DNN to burn more energy, take more time, or both. They affect a wide range of DNN applications, from image recognition to natural language processing … Read More “Availability Attacks against Neural Networks” »

Facebook Announces Messenger Security Features that Don’t Compromise Privacy

Posted on By infossl
encryption, facebook, machinelearning, metadata, Security technology, securityengineering

Note that this is “announced,” so we don’t know when it’s actually going to be implemented. Facebook today announced new features for Messenger that will alert you when messages appear to come from financial scammers or potential child abusers, displaying warnings in the Messenger app that provide tips and suggest you block the offenders. The … Read More “Facebook Announces Messenger Security Features that Don’t Compromise Privacy” »

Fooling NLP Systems Through Word Swapping

Posted on By infossl
academicpapers, algorithms, artificialintelligence, machinelearning, Security technology

MIT researchers have built a system that fools natural-language processing systems by swapping words with synonyms: The software, developed by a team at MIT, looks for the words in a sentence that are most important to an NLP classifier and replaces them with a synonym that a human would find natural. For example, changing the … Read More “Fooling NLP Systems Through Word Swapping” »

Vulnerability Finding Using Machine Learning

Posted on By infossl
artificialintelligence, cloudcomputing, cybersecurity, machinelearning, microsoft, Security technology, securityengineering, vulnerabilities

Microsoft is training a machine-learning system to find software bugs: At Microsoft, 47,000 developers generate nearly 30 thousand bugs a month. These items get stored across over 100 AzureDevOps and GitHub repositories. To better label and prioritize bugs at that scale, we couldn’t just apply more people to the problem. However, large volumes of semi-curated … Read More “Vulnerability Finding Using Machine Learning” »

Deep Learning to Find Malicious Email Attachments

Posted on By infossl
email, gmail, google, machinelearning, malware, phishing, Security technology

Google presented its system of using deep-learning techniques to identify malicious email attachments: At the RSA security conference in San Francisco on Tuesday, Google’s security and anti-abuse research lead Elie Bursztein will present findings on how the new deep-learning scanner for documents is faring against the 300 billion attachments it has to process each week. … Read More “Deep Learning to Find Malicious Email Attachments” »

Using Machine Learning to Detect IP Hijacking

Posted on By infossl
academicpapers, bgp, crime, machinelearning, Security technology

This is interesting research: In a BGP hijack, a malicious actor convinces nearby networks that the best path to reach a specific IP address is through their network. That’s unfortunately not very hard to do, since BGP itself doesn’t have any security procedures for validating that a message is actually coming from the place it … Read More “Using Machine Learning to Detect IP Hijacking” »